In [7]:
## Distribution plots to compare original vs synthetic data vissually
def plot_distplot_pairs(df1, df2, data1_name, data2_name, save_path):
# Set the seaborn theme
sns.set_theme(style='whitegrid')
# Get the common columns between the two dataframes
common_columns = df1.columns.intersection(df2.columns)
# Create the directory if it doesn't exist
os.makedirs(save_path, exist_ok=True)
# Create a zip file to store the plots
with zipfile.ZipFile(f'{save_path}/distplots.zip', 'w') as zipf:
# Iterate over each common column
for column in common_columns:
# Create subplots for each pair of distplots
fig, axs = plt.subplots(1, 2, figsize=(10, 4))
# Plot distplot for df1
sns.distplot(df1[column], ax=axs[0])
axs[0].set_title(f'Distribution of {column} ({data1_name})')
# Plot distplot for df2
sns.distplot(df2[column], ax=axs[1])
axs[1].set_title(f'Distribution of {column} ({data2_name})')
# Adjust spacing between subplots
plt.tight_layout()
# Save the plot as an image
plot_filename = f'{column}.png'
plot_path = f'{save_path}/{plot_filename}'
plt.savefig(plot_path)
# Add the saved image to the zip file
zipf.write(plot_path, arcname=plot_filename)
# Show the plot
plt.show()
# Close the plot
plt.close()
print(f"Plots saved as '{save_path}/distplots.zip'")
data1_name = "Original Data"
data2_name = "Synthetic Data"
save_path = "plots_directory"
plot_distplot_pairs(original_data, synthetic_data, data1_name, data2_name, save_path)
Plots saved as 'plots_directory/distplots.zip'
